Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for tracking a user, comprising: receiving a depth image, the depth image being captured by a depth camera; identifying an estimated location or position of an extremity of the user in the depth image; adjusting a model based on the estimated location or position of the extremity; and based at least on determining that a location or position of the extremity has not been estimated from a second depth image, adjusting the model to move the location or position of the extremity to a default position of the extremity.
A method for tracking a user's movements using a depth camera involves capturing a depth image of the user, then identifying the estimated location of a user's extremity (like a hand or foot) within that image. A digital model (representing the user's body) is adjusted to match the estimated location of the extremity. If the extremity's location isn't detected in a subsequent depth image, the model is adjusted to move that extremity to a predefined default position (e.g., a T-pose). This ensures the model remains stable even when tracking data is incomplete.
2. The method of claim 1 , further comprising: mapping the model to an on screen avatar.
Building upon the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method further includes mapping the digital model of the user to an on-screen avatar. This allows the user's movements to be visualized in real-time on a display.
3. The method of claim 1 , further comprising: providing the model to a gesture library.
Expanding on the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method also provides the digital model to a gesture library. This allows the model's pose and movements to be recognized as specific gestures that can then trigger actions within an application.
4. The method of claim 1 , wherein the model comprises a skeletal model having joints and bones.
In the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, the digital model used is a skeletal model comprising joints and bones. This allows for a more realistic and anatomically accurate representation of the user's body and movements.
5. The method of claim 4 , wherein adjusting the model comprises: adjusting a joint of the skeletal model to the estimated location or position.
Using the skeletal model comprised of joints and bones in the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a skeletal model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, adjusting the model involves moving a specific joint in the skeletal model to the estimated location of the extremity. This allows for precise control over the model's pose.
6. The method of claim 1 , further comprising: determining that the estimated location or position is valid.
Considering the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method incorporates verifying that the estimated location of the extremity is valid before adjusting the model. This prevents the model from being adjusted based on faulty data.
7. The method of claim 1 , further comprising: adjusting the model based on a geometric constraint.
Based on the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method also adjusts the model based on geometric constraints. These constraints can be rules about joint angles, limb lengths, or overall body posture, ensuring the model remains physically realistic.
8. The method of claim 1 , wherein the default pose comprises at least one of the following: a T-Pose, a Di Vinci pose, and a natural pose.
Using the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, the default pose the model moves to can be a T-pose, a DaVinci pose (arms outstretched to the sides), or a natural pose. These are pre-defined postures used when tracking data is lost.
9. The method of claim 1 , further comprising: magnetizing the model to one or more pixels in the depth image.
Within the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method further includes "magnetizing" the model to pixels in the depth image. This means pulling the model towards features detected in the depth image, improving accuracy and preventing the model from drifting away from the user.
10. The method of claim 1 , further comprising: determining that a pose associated with the model is valid.
In addition to the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method incorporates determining that the overall pose of the model is valid. This prevents the model from assuming unnatural or physically impossible poses.
11. The method of claim 1 , further comprising: refining the model based on the received depth image.
Continuing with the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method refines the model based on the received depth image. This involves iterative adjustments to the model's pose and shape to better match the user's actual body.
12. The method of claim 1 , further comprising: downsampling at least two pixels in the depth image before identifying the estimated location or position of the extremity of the user.
With the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method downsamples the depth image (reduces its resolution) before identifying the location of the user's extremity. This reduces computational load and can improve performance.
13. The method of claim 1 , further comprising: based at least on determining that a location or position of a second extremity has been estimated from the second depth image, adjusting the model to move the location or position of the second extremity corresponding to the estimated location or position of the second extremity.
Expanding the user tracking method of receiving a depth image from a depth camera, identifying an estimated location of a user's extremity in the depth image, adjusting a model based on the extremity's location, and if the extremity isn't detected in a second depth image, moving it to a default position, this method includes if a second extremity *is* detected in the second depth image, adjusting the model to match the second extremity's location as well. This means tracking multiple body parts simultaneously for improved accuracy.
14. A computer readable storage device for tracking a user, the computer readable storage medium having stored thereon computer executable instructions that, when executed on a computer, cause the computer to perform operations comprising: receiving a depth image; identifying an estimated location or position of an extremity of the user in the depth image; adjusting a model based on the estimated location or position of the extremity; and based at least on determining that a location or position of the extremity has not been estimated from a second depth image, adjusting the model to move the location or position of the extremity to a default position of the extremity.
A computer-readable storage medium (like a hard drive or flash drive) contains instructions that, when executed, perform the user tracking method. This involves receiving a depth image, identifying an estimated location of a user's extremity in the depth image, adjusting a digital model based on that location, and if the extremity isn't detected in a subsequent depth image, moving it to a default position.
15. The computer readable storage device of claim 14 , further bearing computer-executable instructions that, when executed on the computer, cause the computer to perform operations comprising: mapping the model to an on screen avatar.
The computer-readable storage medium with instructions for tracking a user from the description above (receiving a depth image, identifying an extremity location, adjusting a model, and moving it to a default pose if lost) further includes instructions for mapping the digital model to an on-screen avatar. This allows users to visually see their movements reflected in real time.
16. The computer readable storage device of claim 14 , further bearing computer-executable instructions that, when executed on the computer, cause the computer to perform operations comprising: providing the model to a gesture library.
The computer-readable storage medium with instructions for tracking a user from the description above (receiving a depth image, identifying an extremity location, adjusting a model, and moving it to a default pose if lost) also includes instructions for providing the digital model to a gesture library. This enables the recognition of specific poses and movements as gestures within an application.
17. The computer readable storage device of claim 14 , wherein the model comprises a skeletal model having joints and bones.
As described, the computer-readable storage medium with instructions for tracking a user (receiving a depth image, identifying an extremity location, adjusting a model, and moving it to a default pose if lost) uses a digital model that is a skeletal model, comprising of joints and bones.
18. The computer readable storage device of claim 17 , wherein adjusting the model comprises: adjusting a joint of the skeletal model to the estimated location or position.
Within the computer-readable storage medium with instructions for tracking a user (receiving a depth image, identifying an extremity location, adjusting a skeletal model of joints and bones, and moving it to a default pose if lost), adjusting the skeletal model involves moving a joint to the estimated location of the extremity.
19. The computer readable storage device of claim 14 , further bearing computer-executable instructions that, when executed on the computer, cause the computer to perform operations comprising: determining whether the estimated location or position is valid.
The computer-readable storage medium with instructions for tracking a user (receiving a depth image, identifying an extremity location, adjusting a model, and moving it to a default pose if lost) also contains instructions for verifying that the estimated location of the user's extremity is valid before the model is adjusted.
20. A system for tracking a user comprising: a processor; and a memory communicatively coupled to the processor when the system is operational, bearing processor-executable instructions that, when executed on the processor, cause the system to at least: receive a depth image; identify an estimated location or position an extremity of the user in the depth image; adjust a model based on the estimated location or position of the extremity; and based at least on determining that a location or position of the extremity has not been estimated from a second depth image, adjust the model to move the location or position of the extremity to a default position of the extremity.
A system for tracking a user includes a processor and memory. The memory contains instructions that, when executed by the processor, cause the system to receive a depth image, identify the estimated location of a user's extremity in the depth image, adjust a digital model of the user based on that location, and if the extremity isn't detected in a subsequent depth image, move that part of the model to a default pose.
Unknown
November 18, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.